Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentences that start with conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating transitions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.82
    SPONSORED
    -0.76
     unlawfully
    -0.75
    cedented
    -0.75
     Rodham
    -0.74
    ],"
    -0.70
     Guant
    -0.70
    WASHINGTON
    -0.67
    roit
    -0.67
     unlawful
    -0.65
    POSITIVE LOGITS
     Anyway
    1.10
    Anyway
    1.03
     furthermore
    0.84
     anyways
    0.80
     tho
    0.80
     :(
    0.78
    Also
    0.77
    FY
    0.77
     downside
    0.77
    Honestly
    0.77
    Act Density 0.552%

    No Known Activations